{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T16:49:33Z","timestamp":1761929373638,"version":"build-2065373602"},"publisher-location":"Singapore","reference-count":23,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819537280","type":"print"},{"value":"9789819537297","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-3729-7_3","type":"book-chapter","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T16:44:00Z","timestamp":1761929040000},"page":"27-39","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dual-Chain Reasoning: Enhancing Multimodal Document VQA Through Positive and\u00a0Negative Reasoning Paths"],"prefix":"10.1007","author":[{"given":"Yiyuan","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Hanxiao","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Zhaopeng","family":"Gu","sequence":"additional","affiliation":[]},{"given":"Dong","family":"Yi","sequence":"additional","affiliation":[]},{"given":"Guibo","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Jinqiao","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,1]]},"reference":[{"key":"3_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"3_CR2","unstructured":"Applegarth, G.,\u00a0Weatherstone, C.,\u00a0Hollingsworth, M.,\u00a0Middlebrook, H.,\u00a0Irvin, M.: Exploring synaptic resonance in large language models: a novel approach to contextual memory integration. arXiv preprint arXiv:2502.10699 (2025)"},{"key":"3_CR3","unstructured":"Cao, J.,\u00a0Xiao, J.: An augmented benchmark dataset for geometric question answering through dual parallel text encoding. In: Proceedings of the 29th International Conference on Computational Linguistics, pp. 1511\u20131520 (2022)"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Q.,\u00a0Qin, L.,\u00a0Zhang, J.,\u00a0Chen, Z.,\u00a0Xu, X.,\u00a0Che, W.: M$${\\Theta }\\!\\!3$$ cot: a novel benchmark for multi-domain multi-step multi-modal chain-of-thought. arXiv preprint arXiv:2405.16473 (2024)","DOI":"10.18653\/v1\/2024.acl-long.446"},{"key":"3_CR5","unstructured":"Ge, J.,\u00a0Luo, H.,\u00a0Qian, S.,\u00a0Gan, Y.,\u00a0Fu, J.,\u00a0Zhang, S.: Chain of thought prompt tuning in vision language models. arXiv preprint arXiv:2304.07919 (2023)"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Goyal, Y.,\u00a0Khot, T.,\u00a0Summers-Stay, D.,\u00a0Batra, D.,\u00a0Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6904\u20136913 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"3_CR7","unstructured":"Guo, D., et\u00a0al.: DeepSeek-R1: incentivizing reasoning capability in LLMs via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6700\u20136709 (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Johnson, J.,\u00a0Hariharan, B.,\u00a0Van Der\u00a0Maaten, L.,\u00a0Fei-Fei, L.,\u00a0Lawrence\u00a0Zitnick, C.,\u00a0Girshick, R.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2901\u20132910 (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"3_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1007\/978-3-319-46493-0_15","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Kembhavi","year":"2016","unstructured":"Kembhavi, A., Salvato, M., Kolve, E., Seo, M., Hajishirzi, H., Farhadi, A.: A diagram is worth a dozen images. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part IV. LNCS, vol. 9908, pp. 235\u2013251. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_15"},{"key":"3_CR11","unstructured":"Li, J.,\u00a0Li, D.,\u00a0Xiong, C.,\u00a0Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"3_CR12","first-page":"34892","volume":"36","author":"H Liu","year":"2023","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural. Inf. Process. Syst. 36, 34892\u201334916 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR13","unstructured":"Liu, Y., et al.: TextMonkey: an OCR-free large multimodal model for understanding document. arXiv preprint arXiv:2403.04473 (2024)"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Masry, A., Long, D.X., Tan, J.Q.,\u00a0Joty, S.,\u00a0Hoque, E.: ChartQA: a benchmark for question answering about charts with visual and logical reasoning. arXiv preprint arXiv:2203.10244 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Mathew, M.,\u00a0Bagal, V.,\u00a0Tito, R.,\u00a0Karatzas, D.,\u00a0Valveny, E.,\u00a0Jawahar, C.: InfographicVQA. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1697\u20131706 (2022)","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Mathew, M.,\u00a0Karatzas, D.,\u00a0Jawahar, C.: DocVQA: a dataset for VQA on document images. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2200\u20132209 (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Renze, M.,\u00a0Guven, E.: Self-reflection in LLM agents: effects on problem-solving performance. arXiv preprint arXiv:2405.06682 (2024)","DOI":"10.1109\/FLLM63129.2024.10852426"},{"issue":"3","key":"3_CR18","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1007\/s00799-022-00329-y","volume":"23","author":"T Saikh","year":"2022","unstructured":"Saikh, T., Ghosal, T., Mittal, A., Ekbal, A., Bhattacharyya, P.: ScienceQA: a novel resource for question answering on scholarly articles. Int. J. Digit. Libr. 23(3), 289\u2013301 (2022)","journal-title":"Int. J. Digit. Libr."},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards VQA models that can read. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8317\u20138326 (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"3_CR20","unstructured":"Team, G., et\u00a0al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"3_CR21","first-page":"61501","volume":"36","author":"W Wang","year":"2023","unstructured":"Wang, W., et al.: VisionLLM: large language model is also an open-ended decoder for vision-centric tasks. Adv. Neural. Inf. Process. Syst. 36, 61501\u201361513 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR22","unstructured":"Wang, X., et al.: Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171 (2022)"},{"key":"3_CR23","unstructured":"Wu, Q.,\u00a0et al.: Grounded chain-of-thought for multimodal large language models. arXiv preprint arXiv:2503.12799 (2025)"}],"container-title":["Lecture Notes in Computer Science","Image and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3729-7_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T16:44:04Z","timestamp":1761929044000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3729-7_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,1]]},"ISBN":["9789819537280","9789819537297"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3729-7_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,1]]},"assertion":[{"value":"1 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIG","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image and Graphics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xuzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icig2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icig.csig.org.cn\/2025\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}